Flexible human–robot cooperation models for assisted shop-floor tasks

Abstract

The Industry 4.0 paradigm emphasizes the crucial benefits that collaborative robots, i.e., robots able to work alongside and together with humans, could bring to the whole production process. In this context, an enabling technology yet unreached is the design of flexible robots able to deal at all levels with humans' intrinsic variability, which is not only a necessary element for a comfortable working experience for the person, but also a precious capability for efficiently dealing with unexpected events. In this paper, a sensing, representation, planning and control architecture for flexible human-robot cooperation, referred to as FlexHRC, is proposed. FlexHRC relies on wearable sensors for human action recognition, AND/OR graphs for the representation of and reasoning upon cooperation models, and a Task Priority framework to decouple action planning from robot motion planning and control.

On the manipulation of articulated objects in human–robot cooperation scenarios

“…Approaches in the first class aim at defining cooperation models, i.e., data structures modelling the task to be jointly carried out, while keeping flexibility and human preferences into account [44,45,3,10,15,46,11].…”

“…However, differently from the approach in [15], the work by Sebastiani and colleagues support on-line changes during plan execution. Finally, the work by Darvish and colleagues represents cooperation models using AND/OR graphs, and allows for a switch among different cooperation sequences at runtime [11], therefore allowing humans to redefine the sequence of tasks among a predefined set of choices. The human does not have to explicitly signal the switch to the robot, whereas the robot adapts to the new cooperation context reactively.…”

“…The first case originates from motion planning or execution issues, e.g., because of a cluttered workspace [17] or to prevent any harm to the human operator [6,7,11]. If motion issues occur, planHRC does not generate a state compatible with s e j+1 .…”

“…As far as the cooperation process is concerned, two high-level directives must be taken into account: D 1 cooperation models (and robot action planning techniques) enforcing the prescribed objectives must be adopted [10,11]; D 2 the robot must be flexible enough to adapt to human operator actions avoiding a purely reactive approach [12,13], and to make its intentions clear [14,15].…”

Detection, localisation and tracking of pallets using machine learning techniques and 2D range data

“…However, the tenets of the Industry 4.0 paradigm are expected to require relaxing such assumptions. Given the goal of providing customers with personalised and just-intime delivery of products, it is foreseen that warehouse environments will become more dynamic and human-friendly, and will host human-robot collaborative processes to a great extent [18,27,31]. As far as AGVs are concerned, such directives imply higher standards in autonomy, as well as more robust perception and decision making capabilities.…”